Skip to content

fix(gateway): honor stt.enabled: false — skip transcription when STT disabled#1110

Closed
teyrebaz33 wants to merge 1 commit into
NousResearch:mainfrom
teyrebaz33:fix/stt-config-ignored
Closed

fix(gateway): honor stt.enabled: false — skip transcription when STT disabled#1110
teyrebaz33 wants to merge 1 commit into
NousResearch:mainfrom
teyrebaz33:fix/stt-config-ignored

Conversation

@teyrebaz33

@teyrebaz33 teyrebaz33 commented Mar 12, 2026

Copy link
Copy Markdown
Contributor

Fixes #1100

Problem

The gateway ignored stt.enabled: false in config.yaml and always attempted to call OpenAI Whisper API for voice messages, causing 401 errors when no valid API key was configured.

Fix

  • Added stt_enabled: bool = True field to GatewayConfig (defaults to True — no behavior change for existing users)
  • GatewayConfig.from_dict now reads stt.enabled from config YAML
  • Gateway skips transcription entirely when stt_enabled is False

Usage

stt:
  enabled: false

Testing

  • 6 new tests covering disabled/enabled/default/from_dict scenarios
  • Full suite: 3220 passed, 0 failed (1 pre-existing failure unrelated to this PR)

Notes

Pluggable STT providers (Deepgram, local Whisper) and auto-disable when no API key is present are follow-up improvements beyond the scope of this fix.

@imadreamerboy imadreamerboy mentioned this pull request Mar 13, 2026
Closed
@AxDSan AxDSan mentioned this pull request Mar 13, 2026
Closed
7 tasks
@teknium1 teknium1 mentioned this pull request Mar 15, 2026
Merged
@teknium1

teknium1 commented Mar 15, 2026

Copy link
Copy Markdown
Contributor

Merged via PR #1394. I salvaged the core stt.enabled gateway fix onto current main, updated it for the current config/runtime flow, and preserved your substantive contribution in the merged history.

The merged result also adds follow-up hardening on top:

  • bridge stt.enabled from config.yaml into GatewayConfig
  • skip gateway transcription cleanly when STT is disabled
  • propagate the disabled flag through shared transcription helpers / voice-mode diagnostics
  • add regression tests for config loading and disabled transcription behavior

Thanks — this was the right bug to fix, it just needed updating for the current codebase.

@teknium1 teknium1 closed this Mar 15, 2026
teknium1 pushed a commit that referenced this pull request Apr 22, 2026
@kshitijk4poor @teknium1
perf(browser): upgrade agent-browser 0.13 -> 0.26, wire daemon idle t…
284e084 
…imeout

Upgrades agent-browser from 0.13.0 to 0.26.0, picking up 13 releases of
daemon reliability fixes:

- Daemon hang on Linux from waitpid(-1) race in SIGCHLD handler (#1098)
- Chrome killed after ~10s idle due to PR_SET_PDEATHSIG thread tracking (#1157)
- Orphaned Chrome processes via process-group kill on shutdown (#1137)
- Stale daemon after upgrade via .version sidecar and auto-restart (#1134)
- Idle timeout not firing (sleep future recreated each loop) (#1110)
- Navigation hanging on lifecycle events that never fire (#1059, #1092)
- CDP attach hang on Chrome 144+ (#1133)
- Windows daemon TCP bind with Hyper-V port conflicts (#1041)
- Shadow DOM traversal in accessibility tree snapshots
- doctor command for user self-diagnosis

Also wires AGENT_BROWSER_IDLE_TIMEOUT_MS into the browser subprocess
environment so the daemon self-terminates after our configured inactivity
timeout (default 300s). This is the daemon-side counterpart to the
Python-side inactivity reaper — the daemon kills itself and its Chrome
children when no commands arrive, preventing orphan accumulation even
when the Python process dies without running atexit handlers.

Addresses #7343 (daemon socket hangs, shadow DOM) and #13793 (orphan
accumulation from force-killed sessions).
ulasbilgen pushed a commit to ulasbilgen/hermes-adhd-agent that referenced this pull request May 1, 2026
@kshitijk4poor @teknium1
perf(browser): upgrade agent-browser 0.13 -> 0.26, wire daemon idle t…
218d784 
…imeout

Upgrades agent-browser from 0.13.0 to 0.26.0, picking up 13 releases of
daemon reliability fixes:

- Daemon hang on Linux from waitpid(-1) race in SIGCHLD handler (NousResearch#1098)
- Chrome killed after ~10s idle due to PR_SET_PDEATHSIG thread tracking (NousResearch#1157)
- Orphaned Chrome processes via process-group kill on shutdown (NousResearch#1137)
- Stale daemon after upgrade via .version sidecar and auto-restart (NousResearch#1134)
- Idle timeout not firing (sleep future recreated each loop) (NousResearch#1110)
- Navigation hanging on lifecycle events that never fire (NousResearch#1059, NousResearch#1092)
- CDP attach hang on Chrome 144+ (NousResearch#1133)
- Windows daemon TCP bind with Hyper-V port conflicts (NousResearch#1041)
- Shadow DOM traversal in accessibility tree snapshots
- doctor command for user self-diagnosis

Also wires AGENT_BROWSER_IDLE_TIMEOUT_MS into the browser subprocess
environment so the daemon self-terminates after our configured inactivity
timeout (default 300s). This is the daemon-side counterpart to the
Python-side inactivity reaper — the daemon kills itself and its Chrome
children when no commands arrive, preventing orphan accumulation even
when the Python process dies without running atexit handlers.

Addresses NousResearch#7343 (daemon socket hangs, shadow DOM) and NousResearch#13793 (orphan
accumulation from force-killed sessions).
aj-nt pushed a commit to aj-nt/hermes-agent that referenced this pull request May 1, 2026
@kshitijk4poor @teknium1
perf(browser): upgrade agent-browser 0.13 -> 0.26, wire daemon idle t…
875d6e7 
…imeout

Upgrades agent-browser from 0.13.0 to 0.26.0, picking up 13 releases of
daemon reliability fixes:

- Daemon hang on Linux from waitpid(-1) race in SIGCHLD handler (NousResearch#1098)
- Chrome killed after ~10s idle due to PR_SET_PDEATHSIG thread tracking (NousResearch#1157)
- Orphaned Chrome processes via process-group kill on shutdown (NousResearch#1137)
- Stale daemon after upgrade via .version sidecar and auto-restart (NousResearch#1134)
- Idle timeout not firing (sleep future recreated each loop) (NousResearch#1110)
- Navigation hanging on lifecycle events that never fire (NousResearch#1059, NousResearch#1092)
- CDP attach hang on Chrome 144+ (NousResearch#1133)
- Windows daemon TCP bind with Hyper-V port conflicts (NousResearch#1041)
- Shadow DOM traversal in accessibility tree snapshots
- doctor command for user self-diagnosis

Also wires AGENT_BROWSER_IDLE_TIMEOUT_MS into the browser subprocess
environment so the daemon self-terminates after our configured inactivity
timeout (default 300s). This is the daemon-side counterpart to the
Python-side inactivity reaper — the daemon kills itself and its Chrome
children when no commands arrive, preventing orphan accumulation even
when the Python process dies without running atexit handlers.

Addresses NousResearch#7343 (daemon socket hangs, shadow DOM) and NousResearch#13793 (orphan
accumulation from force-killed sessions).
02356abc pushed a commit to 02356abc/hermes-agent that referenced this pull request May 14, 2026
@kshitijk4poor @teknium1
perf(browser): upgrade agent-browser 0.13 -> 0.26, wire daemon idle t…
3671ab2 
…imeout

Upgrades agent-browser from 0.13.0 to 0.26.0, picking up 13 releases of
daemon reliability fixes:

- Daemon hang on Linux from waitpid(-1) race in SIGCHLD handler (NousResearch#1098)
- Chrome killed after ~10s idle due to PR_SET_PDEATHSIG thread tracking (NousResearch#1157)
- Orphaned Chrome processes via process-group kill on shutdown (NousResearch#1137)
- Stale daemon after upgrade via .version sidecar and auto-restart (NousResearch#1134)
- Idle timeout not firing (sleep future recreated each loop) (NousResearch#1110)
- Navigation hanging on lifecycle events that never fire (NousResearch#1059, NousResearch#1092)
- CDP attach hang on Chrome 144+ (NousResearch#1133)
- Windows daemon TCP bind with Hyper-V port conflicts (NousResearch#1041)
- Shadow DOM traversal in accessibility tree snapshots
- doctor command for user self-diagnosis

Also wires AGENT_BROWSER_IDLE_TIMEOUT_MS into the browser subprocess
environment so the daemon self-terminates after our configured inactivity
timeout (default 300s). This is the daemon-side counterpart to the
Python-side inactivity reaper — the daemon kills itself and its Chrome
children when no commands arrive, preventing orphan accumulation even
when the Python process dies without running atexit handlers.

Addresses NousResearch#7343 (daemon socket hangs, shadow DOM) and NousResearch#13793 (orphan
accumulation from force-killed sessions).
gweeteve pushed a commit to gweeteve/hermes-agent that referenced this pull request Jun 2, 2026
@kshitijk4poor @teknium1
perf(browser): upgrade agent-browser 0.13 -> 0.26, wire daemon idle t…
0abfbdd 
…imeout

Upgrades agent-browser from 0.13.0 to 0.26.0, picking up 13 releases of
daemon reliability fixes:

- Daemon hang on Linux from waitpid(-1) race in SIGCHLD handler (NousResearch#1098)
- Chrome killed after ~10s idle due to PR_SET_PDEATHSIG thread tracking (NousResearch#1157)
- Orphaned Chrome processes via process-group kill on shutdown (NousResearch#1137)
- Stale daemon after upgrade via .version sidecar and auto-restart (NousResearch#1134)
- Idle timeout not firing (sleep future recreated each loop) (NousResearch#1110)
- Navigation hanging on lifecycle events that never fire (NousResearch#1059, NousResearch#1092)
- CDP attach hang on Chrome 144+ (NousResearch#1133)
- Windows daemon TCP bind with Hyper-V port conflicts (NousResearch#1041)
- Shadow DOM traversal in accessibility tree snapshots
- doctor command for user self-diagnosis

Also wires AGENT_BROWSER_IDLE_TIMEOUT_MS into the browser subprocess
environment so the daemon self-terminates after our configured inactivity
timeout (default 300s). This is the daemon-side counterpart to the
Python-side inactivity reaper — the daemon kills itself and its Chrome
children when no commands arrive, preventing orphan accumulation even
when the Python process dies without running atexit handlers.

Addresses NousResearch#7343 (daemon socket hangs, shadow DOM) and NousResearch#13793 (orphan
accumulation from force-killed sessions).
Egavasyug pushed a commit to Egavasyug/hermes-agent that referenced this pull request Jun 10, 2026
@kshitijk4poor @teknium1
perf(browser): upgrade agent-browser 0.13 -> 0.26, wire daemon idle t…
3dc9bce 
…imeout

Upgrades agent-browser from 0.13.0 to 0.26.0, picking up 13 releases of
daemon reliability fixes:

- Daemon hang on Linux from waitpid(-1) race in SIGCHLD handler (NousResearch#1098)
- Chrome killed after ~10s idle due to PR_SET_PDEATHSIG thread tracking (NousResearch#1157)
- Orphaned Chrome processes via process-group kill on shutdown (NousResearch#1137)
- Stale daemon after upgrade via .version sidecar and auto-restart (NousResearch#1134)
- Idle timeout not firing (sleep future recreated each loop) (NousResearch#1110)
- Navigation hanging on lifecycle events that never fire (NousResearch#1059, NousResearch#1092)
- CDP attach hang on Chrome 144+ (NousResearch#1133)
- Windows daemon TCP bind with Hyper-V port conflicts (NousResearch#1041)
- Shadow DOM traversal in accessibility tree snapshots
- doctor command for user self-diagnosis

Also wires AGENT_BROWSER_IDLE_TIMEOUT_MS into the browser subprocess
environment so the daemon self-terminates after our configured inactivity
timeout (default 300s). This is the daemon-side counterpart to the
Python-side inactivity reaper — the daemon kills itself and its Chrome
children when no commands arrive, preventing orphan accumulation even
when the Python process dies without running atexit handlers.

Addresses NousResearch#7343 (daemon socket hangs, shadow DOM) and NousResearch#13793 (orphan
accumulation from force-killed sessions).
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Reviewers

No reviews

Assignees

No one assigned

Labels

None yet

Projects

None yet

Milestone

No milestone

Development

Successfully merging this pull request may close these issues.

STT config ignored: Gateway hardcodes OpenAI Whisper despite stt.enabled: false

2 participants

@teyrebaz33 @teknium1